© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 217263
    Prev
    Next
    INDEX
    Explanations

    blood transplantation

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers and size increases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    仨
    0.52
     सीआर
    0.44
     deftly
    0.44
     [@
    0.43
    З
    0.43
                     
    0.43
    Ре
    0.43
    ⴻ
    0.42
     Respondents
    0.41
     З
    0.41
    POSITIVE LOGITS
     death
    0.52
     droughts
    0.51
     payback
    0.49
     killings
    0.48
     immortality
    0.47
     protests
    0.46
     hardship
    0.46
     canoes
    0.46
     hinder
    0.45
     alienation
    0.45
    Activations Density 0.001%

    No Known Activations